github地址:https://github.com/ziweizhan/classification
汇总了58个当前主流的分类算法网络结构,还在不断的更新中。
可以训练,测试,操作简单。
支持的网络结构有:
MODEL_NAMES = {
'coatnet':Coatnet,
'swinmlp':Swinmlp,
'swintransformer':Swintransformer,
'mobilenetv3_small':Mobilenetv3_small,
'mobilenetv3_large':Mobilenetv3_large,
'ghostnet':Ghostnet,
'alexnet': Alexnet,
'vgg11':Vgg11,
'vgg11_bn':Vgg11_bn,
'vgg13':Vgg13,
'vgg13_bn':Vgg13_bn,
'vgg-16':Vgg16,
'vgg-16_bn':Vgg16_bn,
'vgg-19':Vgg19,
'vgg-19_bn':Vgg19_bn,
'shufflenet_v2.05': shufflenet_v2_x05,
'shufflenet_v2.10': shufflenet_v2_x10,
'shufflenet_v2.15': shufflenet_v2_x15,
'shufflenet_v2.2': shufflenet_v2_x2,
'squeezenet10':squeezenet10,
'squeezenet11':squeezenet11,
'nest': Nest,
'crossformer': Crossformer,
'regionvit': Regionvit,
'twinssvt': Twinssvt,
'cvt': Cvt,
'levit': Levit,
'pit': Pit,
'crossvit': Crossvit,
'cct': Cct,
'vit': Vit,
'deepvit': Deepvit,
'cait': Cait,
't2tvit':T2tvit,
'convmixer': Convmixer,
'mobilevit_xxs': Mobilevit_xxs,
'mobilevit_xs': Mobilevit_xs,
'mobilevit_s': Mobilevit_s,
'resnext50': Resnext50,
'resnext152': Resnext152,
'resnext101_32x8d': Resnext101_32x8d,
'resnext101_32x16d': Resnext101_32x16d,
'resnext101_32x48d': Resnext101_32x48d,
'resnext101_32x32d': Resnext101_32x32d,
'resnet18': Resnet18,
'resnet34': Resnet34,
'resnet50': Resnet50,
'resnet101': Resnet101,
'resnet152': Resnet152,
'densenet121': Densenet121,
'densenet161': Densenet161,
'densenet169': Densenet169,
'densenet201': Densenet201,
'moblienetv2': Mobilenetv2,
'efficientnet-b7': Efficientnet,
'efficientnet-b8': Efficientnet,
'googlenet': Googlenet,
'inceptionv3':inception3
}
可以使用flask+redis进行api接口的访问。
|